原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Khwan

作者:khwanlabs版本 0.3.12i★ 0i电脑或云端官方网站 ↗
注册名称ai.khwan/khwan-mcp

安装方法

What it does

Durable AI memory: recall distilled facts in a later session or subagent, and remember new ones.

  • Connects 电脑或云端
  • Account or key Cloud: No key needed · Local: Needs KHWAN_API_KEY
  • Category 搜索与 AI 记忆

可搭配使用

教 AI 做这类工作的 Skill,可与本项一起使用

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

作者:google-research★ 35,6011 个 skill

Skill · 操作手册

Shadowbroker

Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to…

作者:BigBodyCobain★ 11,5821 个 skill

Skill · 操作手册

google-maps-scraper

scrape data from Google Maps. Extracts data such as the name, address, phone number, website URL, rating, reviews number, latitude and longitude, reviews,email and more for each place

作者:gosom★ 8,1301 个 skill

Skill · 操作手册

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度0/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度7/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分7/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

用一句话让 AI 帮你安装

请帮我安装 Khwan。按照 https://mcp.popnx.com/i/khwan-mcp.md 操作,先把命令给我看,等我同意后再运行。

粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文

通过 3/3 项检查 · 你的提问会经过开发者的服务器(mcp.khwan.ai) · ✓ 命令已检查 2026年11月14日

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

可连接 Claude,但需要先准备

地址中有 {…} 部分,需要先改成你自己的 · 在 claude.ai 或桌面应用设置一次,即可在聊天中使用 · 免费账户可添加 1 个 · Team/Enterprise 方案由所有者(Owner)添加

  1. 打开 Claude 的 Connectors 页面

    CustomizeConnectors

    CustomizeConnectors1Add2https://…3Add4
  2. 点击“Add” → “Custom” → “Web”,填写这 2 项

    把这里的内容复制到 Claude 中同名的输入框,然后点击 Continue

    Name · 名称Khwan
    Remote MCP server URL · 地址https://mcp.khwan.ai/mcp/{core}/{user}

    在 Claude 检测到的登录设置页点击 Continue · Authentication 按作者说明选择(Sign in now、Sign in when needed 或 No sign in),然后点击 Add

  3. 在聊天中开启

    +ConnectorsKhwan

  4. 试一试

    用 Khwan 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude 说正在使用 Khwan,或回答中出现 Khwan 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

能否连接 ChatGPT 取决于方案

完整 MCP:网页版 ChatGPT Business、Enterprise 或 Edu · Pro:以读取/获取权限连接,修改数据的工具可能用不了 · Plus:官方文档尚未确认,如果在插件页看到添加自定义 MCP 的选项可以试试 · 仅限网页 · 地址中有 {…} 部分,需要先改成你自己的

  1. 在网页版 ChatGPT 打开添加 MCP 的页面

    Plugins+Add custom MCP server

    ChatGPTPlugins1+2https://…3Create4
  2. 填写名称和地址

    输入名称,在 Connection 下粘贴地址,勾选风险提示,然后点击 Create as a plugin

    Name · 名称Khwan
    Connection · 地址https://mcp.khwan.ai/mcp/{core}/{user}
  3. 在聊天中选择 Khwan

    开启新聊天,输入前先从插件列表中选择 Khwan

  4. 试一试

    用 Khwan 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 ChatGPT 说正在使用 Khwan,或回答中出现 Khwan 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 OpenAI 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Claude Code,但需要先准备

地址中有 {…} 部分,需要先改成你自己的

  1. 打开终端

    Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell

  2. 粘贴这条命令并按 Enter

    claude mcp add --transport http --scope user khwan 'https://mcp.khwan.ai/mcp/{core}/{user}'
  3. 在 Claude Code 中输入 /mcp

    应能看到 Khwan 在列表中并显示已连接

  4. 试一试

    用 Khwan 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Claude Code 说正在使用 Khwan,或回答中出现 Khwan 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同

可连接 Cursor,但需要先准备

地址中有 {…} 部分,需要先改成你自己的

  1. 打开 Cursor 的 MCP 设置文件

    ~/.cursor/mcp.json

    粘贴这些设置,填写空着的值并保存

    {
      "mcpServers": {
        "khwan": {
          "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
        }
      }
    }
  2. 在 Cursor 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Khwan 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 Cursor 说正在使用 Khwan,或回答中出现 Khwan 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同

可连接 VS Code,但需要先准备

地址中有 {…} 部分,需要先改成你自己的

  1. 打开 VS Code 的 MCP 设置文件

    MCP: Open User Configuration

    粘贴这些设置,填写空着的值并保存

    {
      "servers": {
        "khwan": {
          "type": "http",
          "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
        }
      }
    }
  2. 在 VS Code 中以 Agent 模式打开 AI 聊天

  3. 试一试

    用 Khwan 告诉我你能帮我做什么,然后做一件给我看

    ✓ 如果 VS Code 说正在使用 Khwan,或回答中出现 Khwan 的工具名称,就表示连接成功

菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

通过网页连接的应用使用的地址

地址https://mcp.khwan.ai/mcp/{core}/{user}

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Khwan 的人💬 讨论 →
开发者专用:终端命令和 JSON 设置

通过网页连接

Claude Code

claude mcp add --transport http --scope user khwan 'https://mcp.khwan.ai/mcp/{core}/{user}'

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "khwan": {
      "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "khwan": {
      "type": "http",
      "url": "https://mcp.khwan.ai/mcp/{core}/{user}"
    }
  }
}

安装在电脑上

Claude Code

claude mcp add --scope user khwan --env KHWAN_API_KEY=your-value -- uvx khwan-mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "khwan": {
      "command": "uvx",
      "args": [
        "khwan-mcp"
      ],
      "env": {
        "KHWAN_API_KEY": "your-value"
      }
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "khwan": {
      "command": "uvx",
      "args": [
        "khwan-mcp"
      ],
      "env": {
        "KHWAN_API_KEY": "your-value"
      }
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "khwan": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "khwan-mcp"
      ],
      "env": {
        "KHWAN_API_KEY": "your-value"
      }
    }
  }
}

需要你填写的值

  • KHWAN_API_KEY 机密 必填 env
    Your Khwan key from https://app.khwan.ai (kwk_live_...). It authenticates you to Khwan; it is not your model provider's key.
  • KHWAN_CORE env
    Select a named core (brain). Paid plans only — the free plan has just `default`, and an unknown slug answers 404. Leave unset to use the default.
  • KHWAN_USER env
    A separate brain inside the core, created on first write — 3 on the free plan, unlimited on paid. Sets the X-Khwan-User header.
  • KHWAN_BASE_URL env
    Override the API base URL, e.g. http://127.0.0.1:8010 for a self-hosted engine.

说明仍为英文原文。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

一览

每周下载量i
32/周
已验证域名
✓ khwan.ai
连接方式
电脑或云端
传输方式
stdio, streamable-http
最新版本i
0.3.12
发布到注册中心i
2026年8月27日
代码最后更新i
2026年8月27日
最近检查
2026年11月15日
作者
khwanlabs
软件包
pypi: khwan-mcp
网站
khwan.ai
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

通过互联网连接,适用于

ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast

在你的电脑上运行,适用于

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

这个地址需要填入你自己的值,所以我们无法替你读取工具列表。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月17日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 khwan.ai 验证(注册中心会核实域名所有权)

  • ✓ 通过

    仍在维护

    代码最后更新于3个月前

  • ✓ 通过

    有许可证

    使用 MIT

  • – 不适用

    端点有响应

    这个地址需要填入你自己的账户信息,所以我们无法替你检查

  • – 不适用

    使用 OAuth 登录

    这个地址需要填入你自己的账户信息,所以我们无法替你检查

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

已公开的漏洞(OSV.dev)

OSV.dev 中没有 khwan-mcp@0.3.12 的记录

只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月16日

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/khwan-mcp.svg)](https://mcp.popnx.com/en/servers/khwan-mcp)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“搜索与 AI 记忆”中的其他服务器比较i

  • 星标数多于此分类中其他 6267 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 6267 个服务器的 31% 更新
  • 基础检查结果等于或优于此分类中其他 6267 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

Khwan 安全吗?

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

你需要填写:KHWAN_API_KEY

它在我的电脑上运行还是在云端?

两种方式都可以:安装在你的电脑上,或者连接云端版本。

它还在维护吗?

GitHub 仓库最后更新于3个月前,最新版本(0.3.12)于3个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,因此也能用于接受远程 MCP 的应用,例如网页版 ChatGPT(Business 及以上为完整 MCP;Pro 为只读)。

有什么可以替代它?

同一分类中有:OpenSEO, Exa, Mockserver, Microsoft Learn MCP, Docs

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

OpenSEO

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

作者:every-app广泛使用★ 2.8万3天前更新

在云端运行✓ everyapp.com

Exa

Connect AI agents to Exa for web search, content fetching, and multi-step research.

作者:exa-labs广泛使用★ 52382个月前更新

在云端运行✓ 服务方 · exa.aiPopNx 团队已实际试用

Mockserver

Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.

作者:mock-server正在增长★ 501121天前更新

在你的电脑上运行✓ 服务方 · mock-server.com

Microsoft Learn MCP

Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.

作者:MicrosoftDocs广泛使用★ 199312个月前更新

在云端运行✓ 服务方 · microsoft.comPopNx 团队已实际试用

Docs

Search and read Empryo's documentation. Read-only, no auth, no local access.

作者:proxysoul正在增长★ 16182个月前更新

在云端运行✓ empryo.com
与相似项目对比
本项
Khwan
OpenSEOExaMockserverMicrosoft Learn MCPDocs
运行位置云端或安装在电脑上都可以在云端运行,无需安装在云端运行,无需安装需要安装在电脑上在云端运行,无需安装在云端运行,无需安装
需要密钥是否否否否否
可在 Claude 中按 + 添加否是是否是否
基础检查3/35/52/43/34/44/4
许可证MITMITMITApache-2.0CC-BY-4.0NOASSERTION
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

khwan-mcp

Durable memory that survives the session. An MCP server that plugs Khwan — a pure AI-memory layer — into Claude Code, Claude Desktop, or any MCP client.

Khwan never runs *your* model. The client is the model. Its job is to persist and distil what matters into a brain you can recall in a later session or seed a subagent with — a compact, bounded set of facts instead of a replayed transcript. One account can hold many isolated cores (brains), and — on paid plans — an isolated sub-brain per end-user.

Nothing on the read or write path costs you an inference call: khwan_recall and khwan_remember make none. Khwan does run one model of its own, on a schedule — a nightly pass that distils stored turns into standing lessons. A real production run was 8 brains and 245 stored turns distilled into 11 lessons, for $0.0094. That pass is Khwan's cost, not yours, and it is the whole difference from memory layers that compress, graph, or consolidate on every turn.

How it saves tokens (and where it doesn't)

Be honest about the mechanism — an MCP adds to a host's context, it cannot replace the transcript the host already sends. So:

  • Within one hot session, it does not save tokens. Claude Code caches its growing history (cache reads ≈ 0.1×), so re-injecting memory every turn only adds. Don't do that here.
  • Across sessions and subagents, it does. A cache dies in minutes; a session ends. Khwan persists distilled facts so the *next* run recalls them cheaply — no cold-replay of an old transcript, and facts that already scrolled out of context are retrievable again.

The token-smart pattern: seed once, remember durable facts (below), rather than running the full loop on every turn of a caching host. The full prepare → record loop still shines in a custom agent on a non-caching host, where replacing history with distilled memory bounds per-turn cost directly.

Install

pip install khwan-mcp          # or: uvx khwan-mcp

Connect to Claude Code

claude mcp add khwan --scope project \

-e KHWAN_CORE=default \ -- khwan-mcp

--scope project writes .mcp.json into the repo, so the setting travels with the project. Note what is not in that command: the key.

Keeping the key out of the repo

claude mcp add -e KHWAN_API_KEY=… writes the literal value into .mcp.json — a file whose whole point is being committed. Two ways to avoid that, and the second is the one that works everywhere:

Shell environment. Leave KHWAN_API_KEY out of the config entirely and export it in the shell that launches claude. The server inherits it.

export KHWAN_API_KEY=kwk_live_xxx

A launcher (works in the desktop app too). A desktop app is started from a dock or menu, not a login shell, so it inherits none of your shell exports and the approach above silently yields no key. Read it from a file instead:

mkdir -p ~/.khwan && chmod 700 ~/.khwan

printf 'KHWAN_API_KEY=kwk_live_xxx\n' > ~/.khwan/env && chmod 600 ~/.khwan/env

cat > ~/.khwan/khwan-mcp <<'SH' #!/bin/sh set -a [ -f "$HOME/.khwan/env" ] && . "$HOME/.khwan/env" set +a exec khwan-mcp "$@" SH chmod 700 ~/.khwan/khwan-mcp

Then point the config at the launcher and keep only non-secret settings inline:

claude mcp add khwan --scope project \

-e KHWAN_CORE=acme -e KHWAN_USER=Web \ -- ~/.khwan/khwan-mcp

.mcp.json is now safe to commit, and every new repo costs two lines instead of a pasted key. Anyone else on the team writes their own ~/.khwan/env.

One brain per project

Memory is only useful if the right project's memory comes back. Two axes, and both give complete isolation:

selected byfreepaid
coreKHWAN_CORE1 — default only5 (starter) → 25 (pro)
sub-brainKHWAN_USER3unlimited

A sub-brain is a full separate brain, not a filter: account::@web shares nothing with account::@api. So the two axes multiply, and a free account already holds four isolated brains — the core on its own, plus three sub-brains:

account              default core, no KHWAN_USER      brain 1

account::@web KHWAN_USER=web brain 2 account::@api KHWAN_USER=api brain 3 account::@docs KHWAN_USER=docs brain 4

Which means one-brain-per-project works on the free plan, for up to four projects — and it needs no `KHWAN_CORE` at all:

# in ~/code/web

claude mcp add khwan --scope project -e KHWAN_USER=web -- ~/.khwan/khwan-mcp

in ~/code/api

claude mcp add khwan --scope project -e KHWAN_USER=api -- ~/.khwan/khwan-mcp

Named cores are the paid axis. Reach for one when four brains stop being enough, or when you want them grouped per client rather than per repository:

# in ~/code/acme-web

claude mcp add khwan --scope project -e KHWAN_CORE=acme -e KHWAN_USER=Web -- ~/.khwan/khwan-mcp

in ~/code/acme-api

claude mcp add khwan --scope project -e KHWAN_CORE=acme -e KHWAN_USER=Api -- ~/.khwan/khwan-mcp

Two things to know before you point KHWAN_CORE anywhere. A core must exist first — an unknown slug answers 404, not "created it for you" — and they are created in the dashboard. On the free plan there is nothing to point at: the cap of one is spent on default, so creating a named core answers 402. Leave KHWAN_CORE unset there and use KHWAN_USER. Sub-brains, by contrast, are created on first write.

Recommended pattern (token-smart)

On a caching host like Claude Code, prefer seed + remember over the per-turn loop:

  1. Seed at the start of a session or subagent:

"Call khwan_recall(query=" ") and use the returned seed_text as

context."

  1. Remember durable facts as they emerge:

"That's a standing decision — call khwan_remember(fact="…")."

Reinforce it in your project's CLAUDE.md, e.g.:

- At the start of a task, call `khwan_recall` to seed relevant memory.
  • When a durable decision/preference/fact emerges, call khwan_remember.
  • Don't call prepare/record every turn — it adds tokens without saving them here.

Seeding a subagent is where the win is clearest — hand it a bounded brief instead of the whole transcript:

"Recall deploy memory with khwan_recall(query="deploy runbook"), then spawn a

subagent whose brief is that seed_text plus the task."

Connect to Claude Desktop

Claude Desktop and Claude Code keep separate MCP configuration — a server added to one is invisible to the other, and claude mcp add does not touch this file. Add to claude_desktop_config.json:

{

"mcpServers": { "khwan": { "command": "/Users/you/.khwan/khwan-mcp", "env": { "KHWAN_CORE": "acme", "KHWAN_USER": "Web" } } } }

Use an absolute path: a desktop app does not get your shell's PATH either, so a bare khwan-mcp may not resolve. One core is selected for the whole app — there is no per-project switch here, so choose a broad one.

Configuration (environment)

VarRequiredPurpose
KHWAN_API_KEYyesYour key from the Khwan dashboard (kwk_live_…).
KHWAN_COREnoSelect a named core. Paid plans only — free has just default.
KHWAN_USERnoA separate brain inside the core — 3 on free, unlimited on paid.
KHWAN_BASE_URLnoOverride the API base — e.g. http://127.0.0.1:8010 for a local engine.

Tools

ToolWhen
khwan_recall(query, limit=3)seed a session/subagent — synthesised lessons + up to 3 relevant facts, as seed_text.
khwan_remember(fact)persist a durable fact/preference for future sessions.
khwan_prepare(input)full loop, before answering — memory context + a turn_token.
khwan_record(turn_token, answer)full loop, after answering — persists the turn so Khwan learns.
khwan_memory(limit=20)inspect what the brain currently remembers.
khwan_cores()list the isolated cores on the account.

khwan_recall / khwan_remember are the token-smart pair for a caching host; khwan_prepare / khwan_record are the full loop for custom agents (pass the exact turn_token from prepare back into record).

What comes back, and what an empty answer means

khwan_recall returns at most three facts — that ceiling is the server's, so limit can lower it but not raise it — plus any lessons synthesis has distilled from many past turns. Lessons lead the seed_text: a rule earned over months outranks a single turn that happens to sit nearby in the index.

Retrieval applies a relevance floor, so an empty `facts` is an answer: the brain has nothing close to this question. Read it as "not known here" rather than as a failure, and do not fill the gap by leaning on whichever fact was nearest.

The floor is deliberately loose, because a memory wrongly dropped is invisible while a memory wrongly kept is not. Expect a returned fact to be *plausibly* related, not certainly relevant — read it before relying on it.

Seeding a brain from work you have already done

A new brain knows nothing, so its first weeks of recall are thin — while the answers are often already sitting in the host's own transcripts, unread. examples/backfill/ replays Claude Code transcripts into a brain: deterministic, no model calls, dry-run by default.

python3 examples/backfill/backfill_claude_code.py --map cores.json

Always-on memory (Claude Code hooks)

The tools above are called *when Claude decides to*. For deterministic memory — no reliance on the model — use the hook preset in examples/claude-code-hooks/: a UserPromptSubmit hook injects memory on every prompt and a Stop hook records every answer.

⚠️ On a caching host this is the *thorough* option, not the *cheap* one — it

adds per-turn tokens. Prefer it when recall reliability matters more than token

cost (or on a non-caching client); otherwise use khwan_recall at session

start.

Source

github.com/khwanlabs/khwan-mcp — this server runs on your machine, with your key, reading what you type. Read it before you install it.

License

MIT — © Khwan Labs. See LICENSE.